gemini-api-dev

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and read public web resources (the REST API discovery spec at https://generativelanguage.googleapis.com/... and the documentation index llms.txt plus linked pages on https://ai.google.dev/gemini-api/docs/), so it ingests open/public third-party content that can materially influence behavior.